Backpropagation: The Intuition
About this video
The intuition of backpropagation: the error flows backward through the network.
Backpropagation shares out the blame for the error among all the weights of a neural network. It propagates an error signal backwards layer by layer, multiplying by the local derivatives, and so obtains the gradient of every weight in a single pass. That idea, published in 1986, is what makes training deep networks possible.
Video transcript
- 0:01 First, the forward pass:
- 0:03 the input flows through the network to the output.
- 0:06 Then the error travels backward, and the chain rule gives each weight its share,
- 0:10 layer by layer.
More videos
Explainer
The Computational Graph and Automatic Differentiation
The computational graph and automatic differentiation, in action.
Explainer
Backpropagation: The Step-by-Step Derivation
The backpropagation derivation, factor by factor with the chain rule.
Explainer
Batch, Stochastic and Mini-Batch Gradient Descent
Batch, stochastic and mini-batch: three ways to traverse the data.
